A new arXiv paper (2609.19384v1) proposes Riemannian–Lorentz Parameter Fusion (RLPF), a geometry-aware method for merging a Vision Transformer and a state-space model into a two-branch hybrid that rea…
Researchers introduce Mixture of Channel Experts (MoCE), a structured sparse channel-mixing layer that replaces pointwise projections in convolutional networks, achieving a 16.7% reduction in MACs and…
D$^3$CL, a parameter-efficient adaptation framework for pretrained diffusion models, achieves 80.1% linear-probing accuracy on ImageNet-1K and an FID of 5.56 for unconditional generation by coupling c…
Researchers propose LEAP, a training curriculum for Vision Transformer feature-based knowledge distillation that uses the teacher's intermediate feature maps as progressively difficult targets. LEAP a…
Researchers introduced the Integral Transform Network (ITNet), a unified architecture that subsumes convolution, attention, and recurrence as special cases of a learnable integral transform. ITNet mat…